Openai WebSearch MCP Server

🚀 OpenAI Web Search MCP Server

An MCP server implemented in TypeScript, offering web search functionality with OpenAI's web search preview feature. This server leverages OpenAI's latest response API and the web_search_preview feature, enabling AI models to conduct real-time web searches via the OpenAI API.

🚀 Quick Start

📦 Installation

You can directly run the package using npx:

npx openai-websearch-mcp-server

Or install it globally:

npm install -g openai-websearch-mcp-server

💻 Usage Examples

Using with MCP Clients

This server is designed to work with MCP (Model Context Protocol) clients. Here's how to configure it with other clients:

Claude Desktop

Add the following configuration to your Claude Desktop settings:

{
  "mcpServers": {
    "openai_websearch": {
      "command": "npx",
      "args": [
        "-y",
        "openai-websearch-mcp-server"
      ],
      "env": {
        "OPENAI_API_KEY": "your_api_key"
      }
    }
  }
}

Replace your_api_key with your actual OpenAI API key.

Environment Configuration

1. Set your OpenAI API key as an environment variable:

export OPENAI_API_KEY='your-api-key-here'

2. Run the server:

openai-websearch-mcp

By default, the server runs on port 3000. You can change the port by setting the PORT environment variable:

PORT=8080 openai-websearch-mcp

📚 Documentation

API

This server provides a web search tool that can be used via the MCP protocol. The tool is named web_search and accepts a query string as input. Under the hood, it uses OpenAI's response API and the web_search_preview feature to perform real-time web searches and retrieve the latest information from various sources on the internet.

🔧 Technical Details

Development

To set up the development environment:

1. Clone the repository.
2. Install dependencies:

npm install

3. Start the development server:

npm run dev

Build

To build the package:

npm run build

📄 License

MIT